INDEX

Explanations

lists or items being referenced

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MigrationBuilder

-0.78

batore

-0.75

imageshack

-0.72

 snippetHide

-0.70

הערות

-0.69

MemoryWarning

-0.65

 khảo

-0.65

FXML

-0.65

сылкі

-0.61

Искәрмәләр

-0.60

POSITIVE LOGITS

 newList

0.98

 LIST

0.84

 Lists

0.83

 mList

0.80

mybatisplus

0.76

 lists

0.72

 itemList

0.71

 list

0.70

lst

0.67

 List

0.67

Activations Density 0.170%

lists or items being referenced

No Comments

No Known Activations